Hugging Face's logo

gchhablani
/
fnet-base-finetuned-mrpc

Text Classification Transformers PyTorch TensorBoard
English fnet generated_from_trainer fnet-bert-base-comparison Eval Results Inference Endpoints
Model card Files Metrics Community
gchhablani commited on
Commit
a277961
•
1 Parent(s): eade57c

Training in progress, epoch 1

Browse files
Files changed (18) hide show
  1. checkpoint-230/config.json +33 -0
  2. checkpoint-230/optimizer.pt +3 -0
  3. checkpoint-230/pytorch_model.bin +3 -0
  4. checkpoint-230/rng_state.pth +3 -0
  5. checkpoint-230/scheduler.pt +3 -0
  6. checkpoint-230/special_tokens_map.json +1 -0
  7. checkpoint-230/tokenizer.json +0 -0
  8. checkpoint-230/tokenizer_config.json +1 -0
  9. checkpoint-230/trainer_state.json +33 -0
  10. checkpoint-230/training_args.bin +3 -0
  11. config.json +33 -0
  12. pytorch_model.bin +3 -0
  13. runs/Sep16_17-30-11_patrick-general-gpu/1631813426.936289/events.out.tfevents.1631813426.patrick-general-gpu.181934.1 +3 -0
  14. runs/Sep16_17-30-11_patrick-general-gpu/events.out.tfevents.1631813426.patrick-general-gpu.181934.0 +3 -0
  15. special_tokens_map.json +1 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +1 -0
  18. training_args.bin +3 -0
checkpoint-230/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-base",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "mrpc",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "not_equivalent",
14
+ "1": "equivalent"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "equivalent": 1,
20
+ "not_equivalent": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 3,
27
+ "torch_dtype": "float32",
28
+ "tpu_short_seq_length": 512,
29
+ "transformers_version": "4.11.0.dev0",
30
+ "type_vocab_size": 4,
31
+ "use_tpu_fourier_optimizations": false,
32
+ "vocab_size": 32000
33
+ }
checkpoint-230/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377ee6742dfd7f11a80a29477595d1edf67ac93c19ebf2458352faf7b27a57ab
3
+ size 662962197
checkpoint-230/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3146fa3219ce503857e21b3237720002d00b02f7f57baa0b1619d9ff8b85a8be
3
+ size 331497705
checkpoint-230/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f56713f94d564b8ad52003dc36b17d54b642a3f317b1d3869d21225ef849ff
3
+ size 14503
checkpoint-230/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f7527121143908b9fa2ffe3131bd6729de5408a0840fcc1891395950eaf4a9
3
+ size 623
checkpoint-230/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
checkpoint-230/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-230/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "google/fnet-base", "model_max_length": 512, "tokenizer_class": "FNetTokenizer"}
checkpoint-230/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 230,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.6000000000000003e-05,
13
+ "loss": 0.544,
14
+ "step": 230
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7328431372549019,
19
+ "eval_combined_score": 0.7813981676914135,
20
+ "eval_f1": 0.8299531981279251,
21
+ "eval_loss": 0.5272471308708191,
22
+ "eval_runtime": 2.9626,
23
+ "eval_samples_per_second": 137.716,
24
+ "eval_steps_per_second": 17.215,
25
+ "step": 230
26
+ }
27
+ ],
28
+ "max_steps": 1150,
29
+ "num_train_epochs": 5,
30
+ "total_flos": 652313525477376.0,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-230/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f60be56a92d65e72efa4b0a6aeb22bf463a1b2d3bd996251ddb8045bd4fad5f
3
+ size 2799
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-base",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "mrpc",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "not_equivalent",
14
+ "1": "equivalent"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "equivalent": 1,
20
+ "not_equivalent": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 3,
27
+ "torch_dtype": "float32",
28
+ "tpu_short_seq_length": 512,
29
+ "transformers_version": "4.11.0.dev0",
30
+ "type_vocab_size": 4,
31
+ "use_tpu_fourier_optimizations": false,
32
+ "vocab_size": 32000
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3146fa3219ce503857e21b3237720002d00b02f7f57baa0b1619d9ff8b85a8be
3
+ size 331497705
runs/Sep16_17-30-11_patrick-general-gpu/1631813426.936289/events.out.tfevents.1631813426.patrick-general-gpu.181934.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e2d10f2568a300d0a6d0f71e548ac1758b732df21a33aa2f3a881eaf3292788
3
+ size 4351
runs/Sep16_17-30-11_patrick-general-gpu/events.out.tfevents.1631813426.patrick-general-gpu.181934.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a5c3531c2629fad91abe3cb967147978b147a71e03e35e1c9f38457921edba
3
+ size 3768
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "google/fnet-base", "model_max_length": 512, "tokenizer_class": "FNetTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f60be56a92d65e72efa4b0a6aeb22bf463a1b2d3bd996251ddb8045bd4fad5f
3
+ size 2799